Call for Papers: Software Engineering for HPC-Enabled Research
Posted by n.chuehong
on 8 August 2019 - 2:53pm
Last call for papers - deadline 16 August!
The Software Sustainability Institute is co-organising a workshop on Software Engineering for HPC-Enabled Research at Supercomputing 2019 in Denver. This workshop is concerned with identifying and applying appropriate software engineering (SE) tools and practices (for example, code generators, static analysers, validation + verification (V&V) practices, testing, design approaches, and maintenance practices) to support and ease the development of reproducible High Performance Computing (HPC) & Data Analysis/Analytics (HPCDA). Specifically:
HPC applications, which include large parallel models/simulations of the physical world running on HPC systems.
HPDA applications that utilise HPC systems (e.g., GPUs computing, compute clusters, cloud computing, containers, or supercomputers) to analyse large amounts of data.
Despite the increasing demand for utilising HPC for such applications, software development for HPC historically attracted little attention from the SE community, while paradoxically, the HPC and HPDA communities have increasingly been adopting SE techniques and tools. Indeed, the development of HPC and HPDA software differs significantly from the development of more traditional business information systems, from which many SE best practices and tools have been drawn.
We encourage submission of papers from members of the SE, HPC, and HPDA communities. Full papers of at most eight pages (IEEE Format, page limit includes figures and references) are solicited to address issues including but not limited to:
Case studies of both successes and/or failures in applying SE tools and practices to the development and/or maintenance of HPC or HPDA software, with sufficient analysis that leads workshop attendees to learn something more general than just the specific case study;
Measures of software development productivity appropriate to HPC or HPDA applications;
Lessons learned from HPC or HPDA applications throughout the product life cycle, from research and development to design, analysis, construction, testing, deployment, continuous integration, and maintenance of software;
SE techniques and tools appropriate for the current range of HPC/HPDC platforms and frameworks;
SE metrics and tool support for HPC and HPDA applications;
Empirical studies that help researchers better understand the environment, tools, languages, and processes used in software development on HPC platforms and how they might be improved; and
V&V techniques target specifically for the HPC or HPDA domains.
In order to increase participation, we will encourage submission of two types of shorter (up to 4 page papers) that will not appear in the proceedings, but will be made available to participants prior to the workshop. First, "position papers" focus on similar topics as the full papers, but state opinions or positions, not necessarily finalised research. These papers should include "POSITION PAPER" in the title. Second, "work in progress" papers focus on similar topics as the full papers, but allow authors to present very early results and challenges to gain feedback or to present tools and practices under development. These papers should include "WIP" in the title.
The organising committee seeks participation from a broad range of stakeholders from across the SE, HPDA, and HPC communities. We especially encourage members of the HPC and HPDA communities to submit practical experience papers. Papers on other related topics are also welcome.
Accepted full papers will be published in a Workshop Proceedings. At least one author of each accepted paper must register as a full participant in the workshop to have the paper appear in the proceedings.